Profile Job Results
Jobs
jpvvrjwrp
Results Ready
Name
ffnet_78s_lowres_w8a8
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 512, 1024, 3]Completion Time
10/25/2025, 9:41:02 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
120 ms
Estimated Peak Memory Usage
7 ‑ 39 MB
Compute Units
GPU
153
| Stage | Time | Memory |
|---|---|---|
First App Load | 20.3 s | 352‑361 MB |
Subsequent App Load | 20.4 s | 350‑382 MB |
Inference | 120 ms | 7‑39 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
Sign up to run this model on a hosted Qualcomm® device!
Run on device